copy

website/docs/faq.md

@@ -63,34 +63,6 @@ has provided this
 [Colab notebook](https://colab.research.google.com/drive/1J9XynhrCqekPL5PR6olHP6eE--rnnjS9?usp=sharing).
 
 
-## Aider isn't editing my files?
-
-Sometimes the LLM will reply with some code changes that don't get applied to your local files.
-In these cases, aider might say something like "Failed to apply edit to *filename*".
-
-This usually happens because the LLM is not specifying the edits
-to make in the format that aider expects.
-GPT-3.5 is especially prone to disobeying the system prompt instructions in this manner, but it also happens with stronger models.
-
-Aider makes every effort to get the LLM
-to conform, and works hard to deal with
-replies that are "almost" correctly formatted.
-If Aider detects an improperly formatted reply, it gives
-the LLM feedback to try again.
-Also, before each release new versions of aider are
-[benchmarked](https://aider.chat/docs/benchmarks.html).
-This helps prevent regressions in the code editing
-performance of an LLM that could have been inadvertantly
-introduced.
-
-But sometimes the LLM just won't cooperate.
-In these cases, here are some things you might try:
-
-  - Use `/drop` to remove files from the chat session which aren't needed for the task at hand. This will reduce distractions and may help GPT produce properly formatted edits.
-  - Use `/clear` to remove the conversation history, again to help GPT focus.
-  - Try the a different LLM.
-
-
 ## Can I change the system prompts that aider uses?
 
 Aider is set up to support different system prompts and edit formats

website/docs/scripting.md

@@ -62,7 +62,7 @@ from aider.models import Model
 # This is a list of files to add to the chat
 fnames = ["greeting.py"]
 
-model = Model("gpt-4-turbo", weak_model="gpt-3.5-turbo")
+model = Model("gpt-4-turbo")
 
 # Create a coder object
 coder = Coder.create(main_model=model, fnames=fnames)
@@ -84,6 +84,6 @@ It can also be helpful to set the equivalend of `--yes` by doing this:
 from aider.io import InputOutput
 io = InputOutput(yes=True)
 # ...
-coder = Coder.create(client=client, fnames=fnames, io=io)
+coder = Coder.create(model=model, fnames=fnames, io=io)
 ```
 

website/docs/troubleshooting.md

@@ -0,0 +1,27 @@
+---
+nav_order: 60
+has_children: true
+---
+
+# Troubleshooting
+
+Below are some approaches for troubleshooting problems with aider.
+If you need more help, please file a
+[GitHub issue]()
+or drop into our
+[Discord]().
+
+When reporting problems, it is very helpful if you can provide:
+
+- Aider version
+- LLM model you are using
+
+The easiest way to do that is to copy the "announcement" lines that
+aider prints when you run it:
+
+```
+Aider v0.37.1-dev
+Models: gpt-4o with diff edit format, weak model gpt-3.5-turbo
+Git repo: .git with 243 files
+Repo-map: using 1024 tokens
+```

website/docs/troubleshooting/edit-errors.md

@@ -0,0 +1,42 @@
+---
+parent: Troubleshooting
+nav_order: 10
+---
+
+# File editing problems
+
+Sometimes the LLM will reply with some code changes
+that don't get applied to your local files.
+In these cases, aider might say something like "Failed to apply edit to *filename*"
+or other error messages.
+
+This usually happens because the LLM is disobeying the system prompts
+and trying to make edits in a format that aider doesn't expect.
+Aider makes every effort to get the LLM
+to conform, and works hard to deal with
+LLMM edits that are "almost" correctly formatted.
+
+But sometimes the LLM just won't cooperate.
+In these cases, here are some things you might try.
+
+## Use a capable model
+
+If possible try using GPT-4o or Opus, as they are the strongest and most
+capable models.
+
+Weaker models
+are more pront to
+disobeying the system prompt instructions.
+Most local models are just barely capable of working with aider,
+so editing errors should be expected.
+
+## Reduce distractions
+
+Many models now have very large context windows,
+but filling them with irrelevant code often
+cofuses the model.
+
+- Don't add too many files to the chat, *just* add the files you think need to be edited.
+Aider also sends the LLM a [map of your entire git repo](https://aider.chat/docs/repomap.html), so other relevant code will be included automatically.
+- Use `/drop` to remove files from the chat session which aren't needed for the task at hand. This will reduce distractions and may help GPT produce properly formatted edits.
+- Use `/clear` to remove the conversation history, again to help GPT focus.

website/docs/troubleshooting/warnings.md

@@ -1,5 +1,5 @@
 ---
-parent: Connecting to LLMs
+parent: Troubleshooting
 nav_order: 900
 ---